The Wispr Flow alternative that keeps your voice on your PC

Published 5 September 2026 · updated 14 October 2026

On a Mac? Wispr Flow, or dictation your Mac keeps to itself

Deixis is a Wispr Flow alternative for Windows that does the same hold-a-key dictation with the recognition on your own PC: no account, no word cap, no audio uploaded. Wispr Flow transcribes every dictation in the cloud, makes you sign in first, and its free plan stops at 2,000 words a week on desktop. Its Context Awareness, on by default, also sends the text around your cursor and on your screen along with the audio.

Hold Ctrl+Win, speak, release. The words are typed at your cursor in whatever app has focus, your editor, your terminal, a ticket, a chat, with the clipboard put back the way you left it. Double-tap the key and it keeps listening until you double-tap again. Nothing is metered, and everything that runs on your PC is free for as long as you use it.

Wispr Flow is genuinely ahead in a few places: a hundred-plus languages, Intel Macs, an iPhone app in the App Store, a signed BAA for HIPAA work, meeting notes you can take into Claude or ChatGPT. This page says so plainly further down. But if what you want is dictation that nobody else hears, on your PC, your Mac or your phone, Deixis is the better tool, and here is the case.

Wispr Flow is also searched for as “Whisper Flow”, “Whispr Flow” or “Wisprflow”.

Why switch

What you gain, and what you give up

Why Deixis

Your voice never leaves your PC. Speech recognition happens inside the app, on your processor. Wispr Flow's privacy page is direct about the alternative: "Transcription always happens in the cloud." Its security overview adds that the service is not end-to-end encrypted, because it has to process the audio to produce a transcript, and that it processes and stores customer data in the United States. Deixis has no audio to process anywhere else, because none is sent. Pull the network cable and it still dictates, records and transcribes meetings, and grabs screens; Wispr Flow's transcription is in the cloud, so offline it can only save your audio to retry later.
What is on your screen stays there. Wispr Flow's Context Awareness help page says the feature is on by default, on Mac and Windows, and lists what can accompany each dictation: the text in the box before, selected and after your cursor, on-screen text, file and variable names in coding apps, your user identifier in the app, the apps in your session, and on a Mac the conversation history. The page now says it works from text and does not take screenshots, but that text still leaves with your audio, and with the feature off Flow still sends the app's name and the website's domain. Deixis is field-aware too, but what leaves is smaller and named: the transcript, your vocabulary, the name of the app and the field, and the last thing you dictated into that field, and only once you have switched cloud cleanup on. Never the window title, never the text on your screen, never the audio.
No account and no word cap, for anything local. Wispr Flow's setup guide makes signing in, with Google, Apple, Microsoft, SSO, or an email and password, a step before you dictate a word, and its free plan then stops at 2,000 words a week on desktop; past that it is $15 per user a month, or $12 a month billed yearly. Deixis never asks, and never counts. Install it, download the speech model once, and you are dictating, with no meter on anything that runs on your device: dictation, hands-free notes, screen grabs, meetings, the dictionary and all the vocabulary packs. The only time it wants an email address is if you choose to start the trial of the cloud extras, and that is a six-digit code, no card, no password. Pro, at $49 a year, buys those extras with nothing to set up.
On-device on every device. Windows, Mac and Android, and an iPhone keyboard in beta, with the same on-device speech recognition on each; your dictation audio never leaves any of them. On Android it is a floating microphone bubble that types into any app, and everything that runs on the phone is free there too, with no weekly allowance to watch. Wispr Flow's free plan allows 1,000 words a week on mobile.
Nothing trains on you. Wispr Flow's help centre says "Improve the model for everyone" is on by default for Free and Pro, with the choice shown during onboarding, and its data-controls page that with it on, your audio, transcripts and edits may be used to train its models; on Enterprise it is off and locked, and on Growth its pricing page gives an admin control over it. Deixis has no such switch because there is nothing behind it: no telemetry, no analytics, no training data.
Cleanup on your terms. Out of the box, Deixis tidies dictation on your PC with rules, no provider and no key. Want a language model to polish every sentence? One setting: Deixis's cloud, a model on your own machine, or your own key. And you choose how often, When it helps, Every time, or Never.
Meetings that know who is talking, on your PC. Wispr Flow's Notetaker identifies speakers too, on Mac and Windows, but its privacy page says transcription always happens in the cloud, and its help centre says meeting transcripts and summaries are stored in Wispr's cloud with no setting to opt out of that storage. Deixis records a meeting with Ctrl+Win+M, your microphone and what comes through the speakers, and transcribes it on your PC as it runs. You name the people in it, and voice identification tells the remote voices apart; once you have named a voice, Deixis recognises that person in later meetings. The voiceprint is a mathematical fingerprint that stays on your machine, is never uploaded, and can be deleted per person. Deixis meetings run on Windows and Android; on the phone they are recorded from its microphone and transcribed there, with notes.
Screen grabs, annotation and screen recording, on the same key. Ctrl+Win+S freezes the screen, you drag a region, add arrows, boxes, numbered steps or a blur. Ctrl+Win+V records the screen to a video, narrated when a microphone is set up for it. And every note, transcript, grab, recording and setting sits in one folder as ordinary files you own: back it up, search it, uninstall Deixis tomorrow and every word is still there.

Where Wispr Flow still wins

A hundred-plus languages. Its pricing page lists speech-to-text across 100+ languages on every plan, the free one included. Deixis ships English speech models; if you dictate in another language, Wispr Flow is the one that will understand you.
Older Macs, Intel ones included. Its requirements page lists macOS 12 Monterey or later, on Apple Silicon or Intel. Deixis on a Mac needs Apple Silicon and macOS 13 or later.
An iPhone app in the App Store. Its setup guide installs the iPhone app from the App Store, and its requirements page supports iPhones on iOS 18.3 or later. Deixis's iPhone keyboard is a beta on TestFlight, not yet in the App Store.
A signed BAA for HIPAA work. Its privacy page says you can sign a Business Associate Agreement for dictation on any plan, and its pricing page lists org-wide HIPAA enforcement with a signed BAA on Growth, at $23 per user a month or $18 billed yearly; accepting one turns its Notetaker off. Deixis offers no BAA. Your audio never leaves your PC, but if your compliance team needs a signed agreement from the vendor, Wispr Flow can sign one and Deixis cannot.
Meeting notes you can take into AI tools. Its pricing page lists, on every plan, meeting notes from its Notetaker that you can use in Claude, ChatGPT and other AI tools over MCP. Deixis writes meeting notes too, on Windows and Android, but has no MCP connection; its integrations are webhooks and buttons that you set up yourself, pointed at URLs you own.
A dictionary that fills itself in. Its data-controls page describes an option that watches your edits and adds corrected spellings to your dictionary automatically, and its Pro plan shares a dictionary and snippets across a team. In Deixis you add a word yourself, one key press, and the dictionary is a file on your machine.

What you get

More than dictation. One key, and everything behind it.

Hold the key and press a letter: free mode, a grab, a meeting, a recording, a translation, your own buttons. All of it on your own device, all of it free, none of it behind an account.

The Deixis panel tethered to the caret in a code editor, listening — Dictation, where your cursor is

Hold a key, speak, release. Clean, punctuated text lands in whatever has focus, on your PC, your Mac and your phone, with your clipboard handed back.

A finished free-mode note with two captured references interleaved with the narration — Free mode: talk and point

Narrate for as long as you like while you grab a region, pick a button on screen or take a selection. One note, what you said interleaved with what you pointed at, pasted where you finish and saved as Markdown.

A frozen screen with a dashed selection, numbered steps, an arrow and a pixelated patch — Screen grabs, annotated

Freeze every screen at the keypress, drag a region, add arrows, boxes, text and numbered steps, and pixelate what is private. Saved as a PNG that stays editable.

The page Deixis writes for a shared recording: a short link, a title, a summary and the video — Screen recording, shared as a link

Record the screen with your narration. The recording writes itself up with a title, chapters and a summary, and from your Deixis account it shares as a link anyone can open without one. The Loom you can stop paying for.

A meeting transcript with timestamps and named speakers, and a level meter — Meetings, no bot, names included

Your microphone and the other side, transcribed on your machine while the call runs. Deixis tells the voices apart and remembers the ones you name, and never uploads a voice.

A custom button definition, a webhook delivery and the vocabulary packs — Your own buttons and workflows

Add a button to the palette: it gets the note on stdin and types back whatever it prints. Send finished notes to any URL you own. Chain steps: read the text off a screenshot, translate it, summarise it, post it.

Side by side

Wispr Flow and Deixis, side by side

Row	Deixis	Wispr Flow
Runs on	Windows 10 and 11 (64-bit, on an Intel or AMD processor with AVX2: 2013 and later; no build for Windows on ARM), Mac (Apple Silicon) and Android (a dictation bubble in any app, plus meetings), with an iPhone keyboard in beta on TestFlight and not yet in the App Store. Meetings run on Windows and Android. One engine on all of them, and dictation audio never leaves the device.	Windows 10 or 11 (x64 only, no ARM), macOS 12 or later, on Apple Silicon or Intel, iOS, Android
Speech recognition happens	On your own device, inside the app, on every platform. Dictation audio never leaves it; a meeting's, only if you turn on cloud processing on Android.	In the cloud
AI cleanup happens	On your device, with no provider at all. Or, if you want more, Deixis's cloud, your own Ollama, or your own key. Your choice, in one setting.	In the cloud
Leaves your machine	Text, and only once you switch a cloud feature on, plus, on Windows, one key you press to check your own Claude plan, and, on Android, a meeting's audio if you turn on cloud processing for meetings. Never a dictation's audio, never screenshots, never window titles.	Audio, text
Account needed	None, ever, for anything that runs on your device. The cloud extras have a seven-day trial you start with an email code. No card.	Required
Price	Free forever for everything local, meetings included. Pro is $49 a year for the cloud extras with nothing to set up.	Free tier: 2,000 words a week on desktop, 1,000 a week on mobile; $15 a month; $144 a year; those are Pro, per user. Growth, which adds single sign-on and org-wide HIPAA enforcement with a signed BAA, is $23 per user a month, or $18 a month billed yearly
Your transcripts live	In plain files, in one folder you own and can back up. Uninstall Deixis and every note is still readable.	On your device and in the cloud
Make it yours	Add your own buttons that run a script, send finished notes to any URL you own, and switch on vocabulary packs for your field.	A personal dictionary and snippets, an auto-add-to-dictionary option that learns from your edits, and meeting notes from its Notetaker that you can use in Claude, ChatGPT and other AI tools over MCP. Pro adds a shared dictionary and snippets for a team.

Wispr Flow facts from wisprflow.ai, its privacy policy, policy, security, context, storage, controls, setup, requirements, app, handsfree and shortcuts, read on 7 October 2026. “Not documented” means those pages did not say.

Wispr Flow transcribes every dictation in its cloud. Its Context Awareness, on by default, sends text from your screen and from the box you are typing in along with the audio; its help page now says the feature works from text and does not take screenshots. Training on your dictations is on by default for Free and Pro, and off and locked on Growth and Enterprise.

What leaves your machine, and what leaves theirs

Deixis publishes every byte it sends, as a table, because there is so little of it. Here is that table beside what Wispr Flow's own pages say.

What	Deixis	Wispr Flow
Audio	A dictation's, never: recognition happens inside the app on your device, and the recording, the model and the transcript stay there. A meeting's, only if you turn on Deixis cloud processing for meetings on Android: its audio, in pieces, each its own request, and Deixis stores and logs none of itapi.deixis-voice.com, then Whisper on Cloudflare Workers AI · only on Android, after a meeting ends, with cloud processing switched on in Settings › Meetings — on Wi-Fi, or on mobile data only if you choose	Your dictation audio. The privacy page and the data-controls page both say transcription always happens in the cloud; the security overview says the service is not end-to-end encrypted, because it must process the audio to produce a transcript, and that it processes and stores customer data in the United States.Wispr's cloud · every dictation
The dictated text	The sentence you just dictated, your vocabulary, and your previous sentence in that fieldthe endpoint you chose · only with a cloud endpoint set, and by default only when the local rules are not enough	The transcript comes back from the cloud. With Dictation Cloud Storage on, dictation transcripts, audio and history are stored on Wispr's servers; with Improve the model for everyone on, audio, transcripts and edits may be used to train its models. Its data-sharing help page says both switches default to on unless your plan or organisation restricts them.Wispr's servers · every dictation; training is on by default for Free and Pro and, per its privacy page, off and locked on Growth and Enterprise; cloud storage is a setting under Data and Privacy
Context around the text	The names of the app and the field the text is going into. Never the window title, never a screenshot.the same endpoint · with that request	With Context Awareness on, which is the default, the help page says context can accompany your dictation: app info, the text in the box before, selected and after the cursor, on-screen text, variable and file names in coding apps, your user identifier within the app, the apps in your current session, and conversation history. It says the feature works from text and does not take screenshots. With it off, Flow still sends the app's name and the website's domain. Standard macOS password fields, sensitive and numeric-only fields, browser URL bars and banking apps are excluded, though custom or web-based password fields may be read like normal text, and captured text is cleared when the dictation ends. On Windows, conversation context and element descriptions are Mac-only today.Wispr, with the dictation · with each dictation, unless you turn Context Awareness off under Settings → Data and Privacy
Telemetry and analytics	None. No account, no telemetry, no analytics, no crash reports.	Usage statistics such as the number of words you have dictated, which the data-controls page says Wispr may collect whatever your data settings. Its data-sharing help page adds that with model improvement off, Flow still uploads dictation metadata: word count, duration, app, URL, timestamp, microphone and detected language among it. The privacy policy names third-party web analytics such as Google Analytics on its Services.Wispr, and Google Analytics on its Services · regardless of your data controls
Update check	Nothing but the request; the version check happens on your PCapi.deixis-voice.com · every launch, and when you ask in Settings	not documented
Model download	Nothing but the requesthuggingface.co · once, when you press Download on first run	Nothing to download: transcription always happens in the cloud, so no speech model lives on your computer.— · —
Account and sign-in	An email address, only if you choose to start the trial, plus the partner tag from a partner download link and the first partner website that connected to Deixis on this computer, if there are anythe Deixis endpoint · when you start the trial	An account is required: signing in with Google, Apple, Microsoft, SSO, or email and password is a setup step on desktop and mobile. The privacy policy lists email address, first and last name and phone number as account information.Wispr · at sign-up, before the first dictation
Integrations	The finished note, and for a screenshot its file name, never the imagea URL you added yourself · on finish, only for destinations you added	Calendar, contact and directory data from Google, if you connect those, per the privacy policy. The pricing page lists meeting notes you can use in Claude, ChatGPT and other AI tools over MCP.Wispr, and the services you connect · only when you connect them

The same table for every tool we have measured

Before you switch

Who should not switch

If you dictate in a language other than English, stay with Wispr Flow: Deixis's speech models are English models. If your work is under HIPAA and your compliance team needs a signed BAA from the vendor, Wispr Flow offers one and Deixis does not. If your Mac has an Intel processor or runs macOS 12, Deixis will not run on it. If most of your dictation happens on an iPhone, Wispr Flow's app is in the App Store and Deixis's keyboard is still a beta. If taking your meeting notes into Claude or ChatGPT, or the shared team dictionary, is the reason you pay, those are things Deixis does not have; and Deixis meetings run on Windows and Android, not on the Mac. On Windows, Deixis needs an Intel or AMD processor with AVX2, from 2013 or later: an older processor will not start it, and there is no build for Windows on ARM, which Wispr Flow does not support either. And there is no Linux build.

Making the switch

Five minutes, and most of it is the one download.

The key

Wispr Flow's help centre gives Ctrl+Win as its push-to-talk key on Windows, so your hands already know the gesture: hold Ctrl+Win, speak, release. Its setup guide says a double-tap of that key toggles hands-free mode, and Deixis works the same way: double-tap the chord to keep listening, and double-tap again to stop. The chord can be remapped in Settings if Ctrl+Win is taken on your machine.

The speech model

First launch shows one Download button. Press it, wait for a file about the size of a short video, and you are dictating. Settings offers a second, larger model that is more accurate and slower to decode, and it swaps in without a restart. That download is the only thing a fresh install fetches until you ask it for something: the calls it makes by itself are an update check and, when you open the Settings window, a check for an announcement from us, and neither of those sends anything but the request.

Your words

There is no importer for a Wispr Flow dictionary, so add words as you go: select one anywhere, press Ctrl+Win+D, done. Five vocabulary packs ship in the box, for software, finance, business, medicine and law, and switching one on takes a click. A word Deixis keeps mishearing gets a replacement rule, corrected once and fixed forever. Your dictionary is a plain file, so you can also paste a whole list into it in one go.

Cleanup

Deixis works with no provider: rules on your PC drop filler words, apply your dictionary, capitalise the first word and close the sentence. If you liked the polish a language model gives every sentence, Settings → Cleanup is one choice: let Deixis run it in the cloud, run a model on your own machine, or use your own key. Whichever you pick, what leaves your PC is the short list in the table on this page, and nothing on it is audio.

Your Wispr subscription

Deixis has nothing to cancel. Your Wispr Flow subscription, and whatever it stored under Dictation Cloud Storage, are managed on Wispr's side, in its own settings.

Before you ask

Questions people search for

Is Wispr Flow safe?

Its pages say data is encrypted in transit and at rest and list its security certifications, and they also say transcription always happens in the cloud, that customer data is processed and stored in the United States, and that the service is not end-to-end encrypted, because it has to process the audio to produce a transcript. "Improve the model for everyone" is on by default for Free and Pro, which lets your audio, transcripts and edits be used for training unless you choose the other option during onboarding or switch it off later. Whether that is safe enough is your call; what is certain is that your voice leaves your machine, and with Deixis a dictation never does, under any setting.

Does Wispr Flow work offline?

Not to turn speech into text: its privacy page says transcription always happens in the cloud, to give the best speed and accuracy, and its hands-free guide says that offline, Flow warns you and saves the audio to retry the transcription. Deixis recognises speech on your own PC, so with no cloud endpoint configured it dictates, records and transcribes meetings, and grabs screens with no connection at all.

Does Wispr Flow read your screen?

It reads text, not pictures. Its Context Awareness help page now says the feature works from text and does not take screenshots, and that, on by default, it can send the text in the box around your cursor, on-screen text, file and variable names in coding apps, the apps in your session and, on a Mac, conversation history with each dictation. You can turn it off under Settings → Data and Privacy, and Flow then still sends the app's name and the website's domain. Deixis sends the transcript, your vocabulary, the name of the app and the field, and your last utterance in that field, only if you have switched cloud cleanup on; never the text on your screen, never the window title.

Is there a free or open-source Wispr Flow alternative?

Wispr Flow's own free plan stops at 2,000 words a week on desktop, then Pro is $15 per user a month, or $12 billed yearly. Deixis is free for everything that runs on your device, with no cap and no account, and Pro is $49 a year, or $10 a month, for the managed cloud extras; it is not open source. If published source matters to you, Handy (MIT licence, on Windows, macOS and Linux) and OpenWhispr (MIT licence, on macOS, Windows and Linux) both say so on their own pages, and both can transcribe on your own computer.

Does Wispr Flow work on Windows?

Yes, on Windows 10 or 11 with an x64 processor; its requirements page says Windows on ARM and Snapdragon machines are unsupported, and its Notetaker needs a PC with 16 GB of memory. Deixis has a floor of its own: an Intel or AMD processor with AVX2, from 2013 on, and no build for Windows on ARM either. On a PC that meets it, Deixis is the whole product: one small installer, and meetings recorded, transcribed and speaker-named on that PC rather than in a cloud.

What is the best Wispr Flow alternative for Windows?

If the thing you want to change is where your voice goes, Deixis: the same hold-a-key dictation with the recognition on your own processor, no word cap, and screen grabs and recordings on the same key, on your PC and your Mac, with meetings on Windows and Android. If you need a hundred languages, a signed BAA, an Intel Mac, or meeting notes you can query from Claude and ChatGPT, Wispr Flow still wins, and this page says so above.

Keep reading

Hold a key. Speak. Keep working.

Deixis is free, needs no account, and runs on your own device. Everything on this page is in the current release.

Download Deixis for Windows or Mac Every byte that leaves

v1.3.2 · 64‑bit Windows 10/11 on Intel or AMD · macOS 13 on Apple silicon · 51 MB · nothing else to install · Android on Google Play

Facts about Wispr Flow checked on 7 October 2026 against wisprflow.ai. Deixis facts are from its documentation for the current release. Something out of date? Tell us.

The Wispr Flow alternative that keeps your voice on your PC